© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4507
    Prev
    Next
    INDEX
    Explanations

    terms and characteristics related to cancer and cellular responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Vulnerability or sensitivity

    np_acts-logits-general · gemini-2.0-flash

    sensitivity and susceptibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doInBackground
    -0.50
     ARISING
    -0.49
    weile
    -0.49
     Satisfaction
    -0.48
    aternary
    -0.48
    CJK
    -0.47
    ocal
    -0.47
    cean
    -0.47
    ΡΑ
    -0.47
    sego
    -0.47
    POSITIVE LOGITS
     sensitivity
    2.15
     sensitive
    2.05
     vulnerability
    2.03
     vulnerable
    1.98
     susceptibility
    1.98
     Sensitivity
    1.92
     Sensitive
    1.90
     susceptible
    1.83
    Sensitive
    1.81
    sensitivity
    1.80
    Activations Density 0.774%

    No Known Activations